Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

How to explain an interaction.

G Fitzmaurice1

  • 1Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts 02115, USA. fitzmaur@hsph.harvard.edu

Nutrition (Burbank, Los Angeles County, Calif.)
|March 10, 2001
PubMed
Summary

This study explains interaction effects in statistical models. It offers simple graphical and tabular methods for discrete variables and proposes using reference levels for quantitative variables to aid interpretation.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The RCSI curriculum for robotic surgery training - setting the standard for future minimally invasive surgeons.

The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland·2025
Same author

Robotic surgery in Ireland: national governance framework and a guide to good practice.

The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland·2025
Same author

Randomized trial of three doses of vitamin D to reduce deficiency in pregnant Mongolian women.

EBioMedicine·2018
Same author

Sex-specific impact of maternal-fetal risk factors on depression and cardiovascular risk 40 years later.

Journal of developmental origins of health and disease·2013
Same author

Predictors of suicide attempts in patients with borderline personality disorder over 16 years of prospective follow-up.

Psychological medicine·2012
Same author

The 10-year course of PTSD in borderline patients and axis II comparison subjects.

Acta psychiatrica Scandinavica·2011

Area of Science:

  • Statistics
  • Data Analysis
  • Quantitative Methods

Background:

  • Interaction effects are crucial for understanding complex relationships in statistical models.
  • Explaining interactions can be challenging, especially when dealing with quantitative variables.

Purpose of the Study:

  • To present accessible tabular and graphical techniques for interpreting interaction effects.
  • To propose a method for handling interactions involving quantitative explanatory variables.

Main Methods:

  • Utilizing simple tabular and graphical techniques for discrete explanatory variables.
  • Proposing the construction of "reference levels" for quantitative explanatory variables.

Main Results:

  • Techniques for discrete variables offer clear qualitative and quantitative interpretations of interactions.
  • The reference level approach facilitates interaction explanation for quantitative variables, similar to discrete cases.

Conclusions:

  • Simple visualization and tabulation methods effectively explain interaction effects for discrete variables.
  • Careful selection of reference levels is essential for interpreting interactions involving quantitative variables.

Related Experiment Videos